g?dZddlmZddlmZddlmZddlmZddl m Z ddl m Z e j eZGd d eZGd d e Zd S)zDeiT model configuration OrderedDict)Mapping)version)PretrainedConfig) OnnxConfig)loggingcDeZdZdZdZ dfd ZxZS) DeiTConfiga? This is the configuration class to store the configuration of a [`DeiTModel`]. It is used to instantiate an DeiT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DeiT [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 16): The size (resolution) of each patch. num_channels (`int`, *optional*, defaults to 3): The number of input channels. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries, keys and values. encoder_stride (`int`, *optional*, defaults to 16): Factor to increase the spatial resolution by in the decoder head for masked image modeling. Example: ```python >>> from transformers import DeiTConfig, DeiTModel >>> # Initializing a DeiT deit-base-distilled-patch16-224 style configuration >>> configuration = DeiTConfig() >>> # Initializing a model (with random weights) from the deit-base-distilled-patch16-224 style configuration >>> model = DeiTModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```deit gelu{Gz?-q=rTc tjdi|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ | |_||_dS)N)super__init__ hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangelayer_norm_eps image_size patch_size num_channelsqkv_biasencoder_stride)selfrrrrrr r!r"r#r$r%r&r'r(kwargs __class__s g/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/deit/configuration_deit.pyrzDeiTConfig.__init__Zs$ ""6"""&!2#6 !2$#6 ,H)!2,$$(  ,)rrrrrrrrrrrrTr)__name__ __module__ __qualname____doc__ model_typer __classcell__)r+s@r,r r s{7 7 rJ%(!-!-!-!-!-!-!-!-!-!-r-r ceZdZejdZedeeee efffdZ ede fdZ dS)DeiTOnnxConfigz1.11returnc0tddddddfgS)N pixel_valuesbatchr&heightwidth)rrrr)s r,inputszDeiTOnnxConfig.inputss.WHQX!Y!YZ    r-cdS)Ng-C6?rr>s r,atol_for_validationz"DeiTOnnxConfig.atol_for_validationstr-N) r.r/r0rparsetorch_onnx_minimum_versionpropertyrstrintr?floatrArr-r,r5r5~s!.v!6!6  WS#X%6 67   X UXr-r5N)r1 collectionsrtypingr packagingrconfiguration_utilsronnxr utilsr get_loggerr.loggerr r5rr-r,rPs######333333  H % %]-]-]-]-]-!]-]-]-@     Z     r-